arXiv subjects

Ting Wang

Publications and source records attributed to Ting Wang.

At least 181 records · Page 10Linked to original sources

arXiv2022

Confidence Matters: Inspecting Backdoors in Deep Neural Networks via Distribution Transfer

Backdoor attacks have been shown to be a serious security threat against deep learning models, and detecting whether a given model has been backdoored becomes a crucial task. Existing defenses are mainly built upon the observation that the backdoor trigger is usually of small size or affects the activation of only a few neurons. However, the above observations are violated in many cases especially for advanced backdoor attacks, hindering the performance and applicability of the existing defenses. In this paper, we propose a backdoor defense DTInspector built upon a new observation. That is, an effective backdoor attack usually requires high prediction confidence on the poisoned training samples, so as to ensure that the trained model exhibits the targeted behavior with a high probability. Based on this observation, DTInspector first learns a patch that could change the predictions of most high-confidence data, and then decides the existence of backdoor by checking the ratio of prediction changes after applying the learned patch on the low-confidence data. Extensive evaluations on five backdoor attacks, four datasets, and three advanced attacking types demonstrate the effectiveness of the proposed defense.

cs.CR↗

arXiv2022

Monolithic Integration of Embedded III-V Lasers on SOI

Silicon photonic integration has gained great success in many application fields owing to the excellent optical device properties and complementary metal-oxide semiconductor (CMOS) compatibility. Realizing monolithic integration of III-V lasers and silicon photonic components on single silicon wafer is recognized as a long-standing obstacle for ultra-dense photonic integration, which can provide considerable economical, energy efficient and foundry-scalable on-chip light sources, that has not been reported yet. Here, we demonstrate embedded InAs/GaAs quantum dot (QD) lasers directly grown on trenched silicon-on-insulator (SOI) substrate, enabling monolithic integration with butt-coupled silicon waveguides. By utilizing the patterned grating structures inside pre-defined SOI trenches and unique epitaxial method via molecular beam epitaxy (MBE), high-performance embedded InAs QD lasers with out-coupled silicon waveguide are achieved on such template. By resolving the epitaxy and fabrication challenges in such monolithic integrated architecture, embedded III-V lasers on SOI with continuous-wave lasing up to 85 oC are obtained. The maximum output power of 6.8 mW can be measured from the end tip of the butt-coupled silicon waveguides, with estimated coupling efficiency of approximately -7.35 dB. The results presented here provide a scalable and low-cost epitaxial method for realization of on-chip light sources directly coupling to the silicon photonic components for future high-density photonic integration.

physics.optics↗

arXiv2022

Manu: A Cloud Native Vector Database Management System

With the development of learning-based embedding models, embedding vectors are widely used for analyzing and searching unstructured data. As vector collections exceed billion-scale, fully managed and horizontally scalable vector databases are necessary. In the past three years, through interaction with our 1200+ industry users, we have sketched a vision for the features that next-generation vector databases should have, which include long-term evolvability, tunable consistency, good elasticity, and high performance. We present Manu, a cloud native vector database that implements these features. It is difficult to integrate all these features if we follow traditional DBMS design rules. As most vector data applications do not require complex data models and strong data consistency, our design philosophy is to relax the data model and consistency constraints in exchange for the aforementioned features. Specifically, Manu firstly exposes the write-ahead log (WAL) and binlog as backbone services. Secondly, write components are designed as log publishers while all read-only analytic and search components are designed as independent subscribers to the log services. Finally, we utilize multi-version concurrency control (MVCC) and a delta consistency model to simplify the communication and cooperation among the system components. These designs achieve a low coupling among the system components, which is essential for elasticity and evolution. We also extensively optimize Manu for performance and usability with hardware-aware implementations and support for complex search semantics.

cs.DB↗

arXiv2022

Gate-Tunable Spin-Orbit Coupling in a Germanium Hole Double Quantum Dot

Hole spins confined in semiconductor quantum dot systems have gained considerable interest for their strong spin-orbit interactions (SOIs) and relatively weak hyperfine interactions. Here we experimentally demonstrate a tunable SOI in a double quantum dot in a Germanium (Ge) hut wire (HW), which could help enable fast all-electric spin manipulations while suppressing unwanted decoherence. Specifically, we measure the transport spectra in the Pauli spin blockade regime in the double quantum dot device.By adjusting the interdot tunnel coupling, we obtain an electric field tuned spin-orbit length lso = 2.0 - 48.9 nm. This tunability of the SOI could pave the way toward the realization of high-fidelity qubits in Ge HW systems.

cond-mat.mes-hall↗

arXiv2022

A Comprehensive Survey of Few-shot Learning: Evolution, Applications, Challenges, and Opportunities

Few-shot learning (FSL) has emerged as an effective learning method and shows great potential. Despite the recent creative works in tackling FSL tasks, learning valid information rapidly from just a few or even zero samples still remains a serious challenge. In this context, we extensively investigated 200+ latest papers on FSL published in the past three years, aiming to present a timely and comprehensive overview of the most recent advances in FSL along with impartial comparisons of the strengths and weaknesses of the existing works. For the sake of avoiding conceptual confusion, we first elaborate and compare a set of similar concepts including few-shot learning, transfer learning, and meta-learning. Furthermore, we propose a novel taxonomy to classify the existing work according to the level of abstraction of knowledge in accordance with the challenges of FSL. To enrich this survey, in each subsection we provide in-depth analysis and insightful discussion about recent advances on these topics. Moreover, taking computer vision as an example, we highlight the important application of FSL, covering various research hotspots. Finally, we conclude the survey with unique insights into the technology evolution trends together with potential future research opportunities in the hope of providing guidance to follow-up research.

cs.LG↗

arXiv2022

FedEntropy: Efficient Device Grouping for Federated Learning Using Maximum Entropy Judgment

Along with the popularity of Artificial Intelligence (AI) and Internet-of-Things (IoT), Federated Learning (FL) has attracted steadily increasing attentions as a promising distributed machine learning paradigm, which enables the training of a central model on for numerous decentralized devices without exposing their privacy. However, due to the biased data distributions on involved devices, FL inherently suffers from low classification accuracy in non-IID scenarios. Although various device grouping method have been proposed to address this problem, most of them neglect both i) distinct data distribution characteristics of heterogeneous devices, and ii) contributions and hazards of local models, which are extremely important in determining the quality of global model aggregation. In this paper, we present an effective FL method named FedEntropy with a novel dynamic device grouping scheme, which makes full use of the above two factors based on our proposed maximum entropy judgement heuristic.Unlike existing FL methods that directly aggregate local models returned from all the selected devices, in one FL round FedEntropy firstly makes a judgement based on the pre-collected soft labels of selected devices and then only aggregates the local models that can maximize the overall entropy of these soft labels. Without collecting local models that are harmful for aggregation, FedEntropy can effectively improve global model accuracy while reducing the overall communication overhead. Comprehensive experimental results on well-known benchmarks show that, FedEntropy not only outperforms state-of-the-art FL methods in terms of model accuracy and communication overhead, but also can be integrated into them to enhance their classification performance.

cs.LG↗

arXiv2022

Model-Contrastive Learning for Backdoor Defense

Due to the popularity of Artificial Intelligence (AI) techniques, we are witnessing an increasing number of backdoor injection attacks that are designed to maliciously threaten Deep Neural Networks (DNNs) causing misclassification. Although there exist various defense methods that can effectively erase backdoors from DNNs, they greatly suffer from both high Attack Success Rate (ASR) and a non-negligible loss in Benign Accuracy (BA). Inspired by the observation that a backdoored DNN tends to form a new cluster in its feature spaces for poisoned data, in this paper we propose a novel two-stage backdoor defense method, named MCLDef, based on Model-Contrastive Learning (MCL). In the first stage, our approach performs trigger inversion based on trigger synthesis, where the resultant trigger can be used to generate poisoned data. In the second stage, under the guidance of MCL and our defined positive and negative pairs, MCLDef can purify the backdoored model by pulling the feature representations of poisoned data towards those of their clean data counterparts. Due to the shrunken cluster of poisoned data, the backdoor formed by end-to-end supervised learning is eliminated. Comprehensive experimental results show that, with only 5% of clean data, MCLDef significantly outperforms state-of-the-art defense methods by up to 95.79% reduction in ASR, while in most cases the BA degradation can be controlled within less than 2%. Our code is available at https://github.com/WeCanShow/MCL.

cs.LG↗

arXiv2022

Multi-agent Reinforcement Learning for Dynamic Resource Management in 6G in-X Subnetworks

The 6G network enables a subnetwork-wide evolution, resulting in a "network of subnetworks". However, due to the dynamic mobility of wireless subnetworks, the data transmission of intra-subnetwork and inter-subnetwork will inevitably interfere with each other, which poses a great challenge to radio resource management. Moreover, most of the existing approaches require the instantaneous channel gain between subnetworks, which are usually difficult to be collected. To tackle these issues, in this paper we propose a novel effective intelligent radio resource management method using multi-agent deep reinforcement learning (MARL), which only needs the sum of received power, named received signal strength indicator (RSSI), on each channel instead of channel gains. However, to directly separate individual interference from RSSI is an almost impossible thing. To this end, we further propose a novel MARL architecture, named GA-Net, which integrates a hard attention layer to model the importance distribution of inter-subnetwork relationships based on RSSI and exclude the impact of unrelated subnetworks, and employs a graph attention network with a multi-head attention layer to exact the features and calculate their weights that will impact individual throughput. Experimental results prove that our proposed framework significantly outperforms both traditional and MARL-based methods in various aspects.

cs.NI↗

arXiv2022

Eliminating Backdoor Triggers for Deep Neural Networks Using Attention Relation Graph Distillation

Due to the prosperity of Artificial Intelligence (AI) techniques, more and more backdoors are designed by adversaries to attack Deep Neural Networks (DNNs).Although the state-of-the-art method Neural Attention Distillation (NAD) can effectively erase backdoor triggers from DNNs, it still suffers from non-negligible Attack Success Rate (ASR) together with lowered classification ACCuracy (ACC), since NAD focuses on backdoor defense using attention features (i.e., attention maps) of the same order. In this paper, we introduce a novel backdoor defense framework named Attention Relation Graph Distillation (ARGD), which fully explores the correlation among attention features with different orders using our proposed Attention Relation Graphs (ARGs). Based on the alignment of ARGs between both teacher and student models during knowledge distillation, ARGD can eradicate more backdoor triggers than NAD. Comprehensive experimental results show that, against six latest backdoor attacks, ARGD outperforms NAD by up to 94.85% reduction in ASR, while ACC can be improved by up to 3.23%.

cs.LG↗

arXiv2022

To Simulate the Spread of Infectious Diseases by the Random Matrix

The main aim to build models capable of simulating the spreading of infectious diseases is to control them. And along this way, the key to find the optimal strategy for disease control is to obtain a large number of simulations of disease transitions under different scenarios. Therefore, the models that can simulate the spreading of diseases under scenarios closer to the reality and are with high efficiency are preferred. In the realistic social networks, the random contact, including contacts between people in the public places and the public transits, becomes the important access for the spreading of infectious diseases. In this paper, a model can efficiently simulate the spreading of infectious diseases under random contacts is proposed. In this approach, the random contact between people is characterized by the random matrix with elements randomly generated and the spread of the diseases is simulated by the Markov process. We report an interesting property of the proposed model: the main indicators of the spreading of the diseases such as the death rate are invariant of the size of the population. Therefore, representative simulations can be conducted on models consist of small number of populations. The main advantage of this model is that it can easily simulate the spreading of diseases under more realistic scenarios and thus is able to give a large number of simulations needed for the searching of the optimal control strategy. Based on this work, the reinforcement learning will be introduced to give the optimal control strategy in the following work.

cs.SI↗

arXiv2022

Transfer Attacks Revisited: A Large-Scale Empirical Study in Real Computer Vision Settings

One intriguing property of adversarial attacks is their "transferability" -- an adversarial example crafted with respect to one deep neural network (DNN) model is often found effective against other DNNs as well. Intensive research has been conducted on this phenomenon under simplistic controlled conditions. Yet, thus far, there is still a lack of comprehensive understanding about transferability-based attacks ("transfer attacks") in real-world environments. To bridge this critical gap, we conduct the first large-scale systematic empirical study of transfer attacks against major cloud-based MLaaS platforms, taking the components of a real transfer attack into account. The study leads to a number of interesting findings which are inconsistent to the existing ones, including: (1) Simple surrogates do not necessarily improve real transfer attacks. (2) No dominant surrogate architecture is found in real transfer attacks. (3) It is the gap between posterior (output of the softmax layer) rather than the gap between logit (so-called $κ$ value) that increases transferability. Moreover, by comparing with prior works, we demonstrate that transfer attacks possess many previously unknown properties in real-world environments, such as (1) Model similarity is not a well-defined concept. (2) $L_2$ norm of perturbation can generate high transferability without usage of gradient and is a more powerful source than $L_\infty$ norm. We believe this work sheds light on the vulnerabilities of popular MLaaS platforms and points to a few promising research directions.

cs.CV↗

arXiv2022

Over-the-Air Federated Learning via Second-Order Optimization

Federated learning (FL) is a promising learning paradigm that can tackle the increasingly prominent isolated data islands problem while keeping users' data locally with privacy and security guarantees. However, FL could result in task-oriented data traffic flows over wireless networks with limited radio resources. To design communication-efficient FL, most of the existing studies employ the first-order federated optimization approach that has a slow convergence rate. This however results in excessive communication rounds for local model updates between the edge devices and edge server. To address this issue, in this paper, we instead propose a novel over-the-air second-order federated optimization algorithm to simultaneously reduce the communication rounds and enable low-latency global model aggregation. This is achieved by exploiting the waveform superposition property of a multi-access channel to implement the distributed second-order optimization algorithm over wireless networks. The convergence behavior of the proposed algorithm is further characterized, which reveals a linear-quadratic convergence rate with an accumulative error term in each iteration. We thus propose a system optimization approach to minimize the accumulated error gap by joint device selection and beamforming design. Numerical results demonstrate the system and communication efficiency compared with the state-of-the-art approaches.

cs.IT↗

arXiv2022

Hybrid integration of deterministic quantum dots-based single-photon sources with CMOS-compatible silicon carbide photonics

Thin film 4H-silicon carbide (4H-SiC) is emerging as a contender for realizing large-scale optical quantum circuits due to its high CMOS technology compatibility and large optical nonlinearities. Though, challenges remain in producing wafer-scale 4H-SiC thin film on insulator (4H-SiCOI) for dense integration of photonic circuits, and in efficient coupling of deterministic quantum emitters that are essential for scalable quantum photonics. Here we demonstrate hybrid integration of self-assembled InGaAs quantum dots (QDs) based single-photon sources (SPSs) with wafer-scale 4H-SiC photonic chips prepared by ion slicing technique. By designing a bilayer vertical coupler, we realize generation and highly efficient routing of single-photon emission in the hybrid quantum photonic chip. Furthermore, we realize a chip-integrated beamsplitter operation for triggered single photons through fabricating a 1x2 multi-mode interferometer (MMI) with a symmetric power splitting ratio of 50:50. The successful demonstration of heterogeneously integrating QDs-based SPSs on 4H-SiC photonic chip prepared by ion slicing technique constitutes an important step toward CMOS-compatible, fast reconfigurable quantum photonic circuits with deterministic SPSs.

physics.optics↗

arXiv2022

The Variable Volatility Elasticity Model from Commodity Markets

In this paper, we propose and study a novel continuous-time model, based on the well-known constant elasticity of variance (CEV) model, to describe the asset price process. The basic idea is that the volatility elasticity of the CEV model can not be treated as a constant from the perspective of stochastic analysis. To address this issue, we deduce the price process of assets from the perspective of volatility elasticity, propose the constant volatility elasticity (CVE) model, and further derive a more general variable volatility elasticity (VVE) model. Moreover, our model can describe the positive correlation between volatility and asset prices existing in the commodity markets, while CEV model can only describe the negative correlation. Through the empirical research on the financial market, many assets, especially commodities, often show this positive correlation phenomenon in some time periods, which shows that our model has strong practical application value. Finally, we provide the explicit pricing formula of European options based on our model. This formula has an elegant form convenient to calculate, which is similarly to the renowned Black-Scholes formula and of great significance to the research of derivatives market.

q-fin.MF↗

arXiv2022

Machine Learning Empowered Intelligent Data Center Networking: A Survey

To support the needs of ever-growing cloud-based services, the number of servers and network devices in data centers is increasing exponentially, which in turn results in high complexities and difficulties in network optimization. To address these challenges, both academia and industry turn to artificial intelligence technology to realize network intelligence. To this end, a considerable number of novel and creative machine learning-based (ML-based) research works have been put forward in recent few years. Nevertheless, there are still enormous challenges faced by the intelligent optimization of data center networks (DCNs), especially in the scenario of online real-time dynamic processing of massive heterogeneous services and traffic data. To best of our knowledge, there is a lack of systematic and original comprehensively investigations with in-depth analysis on intelligent DCN. To this end, in this paper, we comprehensively investigate the application of machine learning to data center networking, and provide a general overview and in-depth analysis of the recent works, covering flow prediction, flow classification, load balancing, resource management, routing optimization, and congestion control. In order to provide a multi-dimensional and multi-perspective comparison of various solutions, we design a quality assessment criteria called REBEL-3S to impartially measure the strengths and weaknesses of these research works. Moreover, we also present unique insights into the technology evolution of the fusion of data center network and machine learning, together with some challenges and potential future research opportunities.

cs.NI↗

arXiv2022

Convergence Rate of Inertial Forward-Backward Algorithms Based on the Local Error Bound Condition

The "Inertial Forward-Backward algorithm" (IFB) is a powerful tool for convex nonsmooth minimization problems, it gives the well known "fast iterative shrinkage-thresholding algorithm " (FISTA), which enjoys $O\left( {\frac{1}{k^2}} \right)$ global convergence rate of function values, however, no convergence of iterates has been proved; by do a small modification, an accelerated IFB called "FISTA\_CD" improves the convergence rate of function values to $o\left( {\frac{1}{k^2}} \right)$ and shows the weak convergence of iterates. The local error bound condition is extremely useful in analyzing the convergence rates of a host of iterative methods for solving optimization problems, and in practical application, a large number of problems with special structure often satisfy the error bound condition. Naturally, using local error bound condition to derive or improve the convergence rate of IFB is a common means. In this paper, based on the local error bound condition, we exploit an new assumption condition for the important parameter $t_k$ in IFB, and establish the improved convergence rate of function values and strong convergence of the iterates generated by the IFB algorithms with six $t_k$ satisfying the above assumption condition in Hilbert space. It is remarkable that, under the local error bound condition, we establish the strong convergence of the iterates generated by the original FISTA, and prove that the convergence rates of function values for FISTA\_CD is actually related to the value of parameter $a,$ and show that the IFB algorithms with some $t_k$ mentioned above can achieve sublinear convergence rate $o\left( {\frac{1}{k^p}} \right)$ for any positive integer $p>1$. Some numerical experiments are conducted to illustrate our results.

math.OC↗

arXiv2022

Seeing is Living? Rethinking the Security of Facial Liveness Verification in the Deepfake Era

Facial Liveness Verification (FLV) is widely used for identity authentication in many security-sensitive domains and offered as Platform-as-a-Service (PaaS) by leading cloud vendors. Yet, with the rapid advances in synthetic media techniques (e.g., deepfake), the security of FLV is facing unprecedented challenges, about which little is known thus far. To bridge this gap, in this paper, we conduct the first systematic study on the security of FLV in real-world settings. Specifically, we present LiveBugger, a new deepfake-powered attack framework that enables customizable, automated security evaluation of FLV. Leveraging LiveBugger, we perform a comprehensive empirical assessment of representative FLV platforms, leading to a set of interesting findings. For instance, most FLV APIs do not use anti-deepfake detection; even for those with such defenses, their effectiveness is concerning (e.g., it may detect high-quality synthesized videos but fail to detect low-quality ones). We then conduct an in-depth analysis of the factors impacting the attack performance of LiveBugger: a) the bias (e.g., gender or race) in FLV can be exploited to select victims; b) adversarial training makes deepfake more effective to bypass FLV; c) the input quality has a varying influence on different deepfake techniques to bypass FLV. Based on these findings, we propose a customized, two-stage approach that can boost the attack success rate by up to 70%. Further, we run proof-of-concept attacks on several representative applications of FLV (i.e., the clients of FLV APIs) to illustrate the practical implications: due to the vulnerability of the APIs, many downstream applications are vulnerable to deepfake. Finally, we discuss potential countermeasures to improve the security of FLV. Our findings have been confirmed by the corresponding vendors.

cs.CR↗

arXiv2022

Towards Fast and Accurate Federated Learning with non-IID Data for Cloud-Based IoT Applications

As a promising method of central model training on decentralized device data while securing user privacy, Federated Learning (FL)is becoming popular in Internet of Things (IoT) design. However, when the data collected by IoT devices are highly skewed in a non-independent and identically distributed (non-IID) manner, the accuracy of vanilla FL method cannot be guaranteed. Although there exist various solutions that try to address the bottleneck of FL with non-IID data, most of them suffer from extra intolerable communication overhead and low model accuracy. To enable fast and accurate FL, this paper proposes a novel data-based device grouping approach that can effectively reduce the disadvantages of weight divergence during the training of non-IID data. However, since our grouping method is based on the similarity of extracted feature maps from IoT devices, it may incur additional risks of privacy exposure. To solve this problem, we propose an improved version by exploiting similarity information using the Locality-Sensitive Hashing (LSH) algorithm without exposing extracted feature maps. Comprehensive experimental results on well-known benchmarks show that our approach can not only accelerate the convergence rate, but also improve the prediction accuracy for FL with non-IID data.

cs.LG↗